OPENGIT/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2025-02-07 06:02:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Updated Textual Inversion (markdown)

AUTOMATIC1111 2022-10-02 20:53:49 +03:00
parent ad0b22fba2
commit b3bd8c0357
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Textual-Inversion.md

@ -49,7 +49,7 @@ Experimental support for training embeddings in user interface.
### Creating an embedding ### Creating an embedding
- **Name**: filename for the created embedding. You will also use this text in prompts when referring to the embedding. - **Name**: filename for the created embedding. You will also use this text in prompts when referring to the embedding.
- **Initialization text*: the embedding you create will initially be filled with vectors of this text. If you create a one vector embedding named "zzzz1234" with "tree" as initialization text, and use it in prompt without training, then prompt "a zzzz1234 by monet" will produce same pictures as "a tree by monet". - **Initialization text**: the embedding you create will initially be filled with vectors of this text. If you create a one vector embedding named "zzzz1234" with "tree" as initialization text, and use it in prompt without training, then prompt "a zzzz1234 by monet" will produce same pictures as "a tree by monet".
- **Number of vectors per token**: the size of embedding. The larger this value, the more information about subject you can fit into the embedding, but also the more words it will take away from your prompt allowance. With stable diffusion, you have a limit of 75 tokens in the prompt. If you use an embedding with 16 vectors in a prompt, that will leave you with space for 75 - 16 = 59. Also from my experience, the larger the number of vectors, the more pictures you need to obtain good results. - **Number of vectors per token**: the size of embedding. The larger this value, the more information about subject you can fit into the embedding, but also the more words it will take away from your prompt allowance. With stable diffusion, you have a limit of 75 tokens in the prompt. If you use an embedding with 16 vectors in a prompt, that will leave you with space for 75 - 16 = 59. Also from my experience, the larger the number of vectors, the more pictures you need to obtain good results.
### Training an embedding ### Training an embedding